Hey :) For a while now I use gpt-oss-20b on my home lab for lightweight coding tasks and some automation. I’m not so up to date with the current self-hosted LLMs and since the model I’m using was released at the beginning of August 2025 (From an LLM development perspective, it feels like an eternity to me) I just wanted to use the collective wisdom of lemmy to maybe replace my model with something better out there.
Edit:
Specs:
GPU: RTX 3060 (12GB vRAM)
RAM: 64 GB
gpt-oss-20b does not fit into the vRAM completely but it partially offloaded and is reasonably fast (enough for me)
Gemma4 e4b quant8 will fit in 12gb and is good
I’d use some Chinese model. Qwen3.5 Claude 4.6 distilled ablitirated is what I use
Qwen is pretty good. Also try LFM models.
I find Qwen3.5 is the best at toolcalling and agent use, otherwise Gemma4 is a very solid all-rounder and it should be the first you try. Tbh gpt-oss is still good to this day, are you running into any problems w it?
No problems per se. I just thought that I had not checked for an update for a longer time.
You’re probably aware, but updating the model periodically is probably a good idea just because things do change overtime.
A model from two years ago was trained on data from at least two years ago. Meaning any technology, code, world event changes wouldn’t be reflected in the model.
I also recommend gemma4 or qwen3.5. Both super solid in my experience for how lightweight they are
Still can’t get my gemma to give me complete unbuggy components
I suggest looking at llm arena leaderboards filtered by open weight models. It offers benchmarks at a very complete and statistically detailed level for models, and usually is quite up to date when new models come out. The new Gemma that just came out might be the best for 1x GPU, and if you have a bunch of vram check out the larger Chinese models
I’d say Qwen 3.5 and Gemma 4 beat GPT OSS in every aspect.
I’m not on there, but you might have more luck in !localllama@sh.itjust.works
You might also want to list the hardware that you plan to use, since that’ll constrain what you can reasonably run.
The latest open weights model from google might be a good fit for you. The 26B model works pretty well on my machine, though the performance isn’t great (6 tokens per second, CPU only).
What sort of coding and what sort of automation tasks? The latter is an easier ticket to fill than the former, though I might have an idea for you on that end if coding is a must
Have you tried the new gemma4 models? The e4b fits in the 12gb memory and is pretty good. Or you can use 31b too, if you’re okay with offloading to CPU.
I’m running gemma4 26b MOE for most of my agent calls. I use glm5:cloud for my development agent because 26b struggles when the context windows gets too big.
How much VRAM?
I’m in the same boat. You’ll get better responses if you post your machine specs. I
What are your computer specs?
I did just update my post with the specs. Maybe it takes a while to federate?
I must have not refreshed ignore my comment
